Individual skill
light-diagram-prompt
Turn research papers, methods, mechanisms, systems, experiments, and user concepts into rigorous, copy-ready prompts for AI image generation of non-data scientific diagrams. Use for method/framework figures, model and system architectures, mechanism/pathway illustrations, research workflows, experimental setup schematics, graphical abstracts, conceptual diagrams, taxonomies, comparison narratives, and reference-guided scientific figures. Also use for 科研绘图提示词、论文方法图、机制图、机理图、技术路线图、 实验流程图、装置示意图、网络结构图、图形摘要、参考图风格迁移。 Deliver prompts first; optionally generate via host tools or configured APIs. Do not use for quantitative charts, plots, or for drawing/rebuilding the final editable figure in Illustrator, PowerPoint, or Visio.
light-diagram/light-diagram-prompt/SKILL.md
Source commit 6597430ad09d8f7c3518ec4cb08829be2b417e18
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 883
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-writing Repository topic
- ai-agent Repository topic
- claude-code Repository topic
- codex Repository topic
- llm-skills Repository topic
- paper-writing Repository topic
- research-tools Repository topic
- scientific-workflow Repository topic
- agent-skills Repository topic
- ai-skills Repository topic
- research Derived category
- data Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.gitignoreasset · 21 bytesREADME.mddoc · 5,747 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesSKILL.mdcore · 20,878 bytesVERIFICATION.mddoc · 6,022 bytesassets/imagegen.example.jsonasset · 247 bytesevaluations/2026-10-27/01-transformer/image-v1.pngasset · 1,201,344 bytesevaluations/2026-10-27/01-transformer/image-v2.pngasset · 1,207,289 bytesevaluations/2026-10-27/01-transformer/image-v3.pngasset · 1,220,175 bytesevaluations/2026-10-27/01-transformer/image-v4-edit.pngasset · 1,502,424 bytesevaluations/2026-10-27/01-transformer/prompt-v1.txtdoc · 1,780 bytesevaluations/2026-10-27/01-transformer/prompt-v2.txtdoc · 2,120 bytesevaluations/2026-10-27/01-transformer/prompt-v3.txtdoc · 2,721 bytesevaluations/2026-10-27/01-transformer/prompt-v4-edit.txtdoc · 1,525 bytesevaluations/2026-10-27/02-crispr/image-v1.pngasset · 1,257,272 bytesevaluations/2026-10-27/02-crispr/image-v2.pngasset · 1,233,992 bytesevaluations/2026-10-27/02-crispr/image-v3.pngasset · 1,263,218 bytesevaluations/2026-10-27/02-crispr/prompt-v1.txtdoc · 1,751 bytesevaluations/2026-10-27/02-crispr/prompt-v2.txtdoc · 2,384 bytesevaluations/2026-10-27/02-crispr/prompt-v3.txtdoc · 3,124 bytesevaluations/2026-10-27/03-perovskite/image-v1.pngasset · 1,711,287 bytesevaluations/2026-10-27/03-perovskite/image-v2.pngasset · 1,546,093 bytesevaluations/2026-10-27/03-perovskite/prompt-v1.txtdoc · 1,786 bytesevaluations/2026-10-27/03-perovskite/prompt-v2.txtdoc · 2,086 bytesevaluations/2026-10-27/04-acoustics/image-v1.pngasset · 1,543,334 bytesevaluations/2026-10-27/04-acoustics/prompt-v1.txtdoc · 1,813 bytesevaluations/2026-10-27/REPORT.mddoc · 7,291 bytesevaluations/2026-10-27/index.htmlasset · 3,642 bytesevaluations/2026-10-27/sources.jsonasset · 1,169 bytesreferences/acceptance-cases.mddoc · 4,896 bytesreferences/diagram-archetypes.mddoc · 6,144 bytesreferences/domain-visual-language.mddoc · 7,864 bytesreferences/generated-image-review.mddoc · 4,686 bytesreferences/image-generation.mddoc · 8,959 bytesreferences/project-layout.mddoc · 5,982 bytesreferences/prompt-quality-check.mddoc · 5,168 bytesreferences/prompt-structure.mddoc · 5,542 bytesreferences/reference-corpus.mddoc · 7,140 bytesreferences/reference-observations.mddoc · 5,773 bytesreferences/research-notes.mddoc · 4,845 bytesreferences/worked-examples.mddoc · 12,795 bytesscripts/image_service.pyruns · 16,296 bytesscripts/search_reference_figures.pyruns · 10,044 bytestests/test_documents.pyruns · 2,832 bytestests/test_image_service.pyruns · 13,475 bytestests/test_search_reference_figures.pyruns · 6,914 bytes
Read excerpt
# Light Diagram Prompt
## 项目目录与续作
需要落盘或继续已有项目时,先读 [项目目录约定](references/project-layout.md),按其中的本阶段位置、版本与关联规则保存;用户指定路径和旧项目优先。包内资源相对本 skill,研究产物相对真实项目,二者不要混用。只做局部讨论时无需初始化目录。
Produce a scientifically faithful, visually intentional, copy-ready image-generation prompt for a **non-data scientific figure**. Always deliver the prompt before generation. Unless the user requests prompt-only, use an available host image tool, otherwise a user-configured image service; without either, deliver the prompt alone. Editable reconstruction belongs to the Illustrator, PowerPoint or Visio skills.
When invoked through the parent [light-diagram workflow](../SKILL.md), reuse its brief, source scope, label list and critical relationships. Use the same generation route and return actual prompt/image paths, hashes and review findings; the parent continues editing-tool selection. Do not generate twice across the handoff. Record revisions separately from executed prompts. Direct prompt-only requests end at the prompt; other direct requests may end at a reviewed generated image.
持续项目先读取有关 Memory,再回实际论文、设计、分析及采用的稿图版本核对。保留实际阅读范围和来源定位、FIG/修订身份、关键关系与证据边界;生成图只作视觉参考。将采用的提示词/图版本、图注需同步事项、未决问题和有来源的决定交回 Write/Review 与 Memory。直接请求无需创建整套交接。
## Scope gate